© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94192
    Prev
    Next
    INDEX
    Explanations

    Recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RECOMMENDED
    -1.20
     recommended
    -1.19
    recommended
    -1.17
     recommendation
    -1.12
    RECOMMENDED
    -1.10
     Recommendation
    -1.06
     themſelves
    -1.05
    recommendation
    -1.05
     recomendada
    -1.05
     itſelf
    -1.03
    POSITIVE LOGITS
    s
    0.64
    e
    0.59
    i
    0.52
    ark
    0.50
     D
    0.49
     to
    0.48
     k
    0.48
    a
    0.46
    <eos>
    0.46
     […]
    0.46
    Activations Density 0.112%

    No Known Activations